Ross ROSS = Recommend OSS · open-source software intelligence for agents

duixcom/Duix-Mobile

🚀 The best real-time interactive AI avatar(digital human) with on-premise deployment and <1.5 s latency. observed · 2026-08-28

github.com/duixcom/Duix-Mobile · homepage · C++ · NOASSERTION (other) observed · 2026-08-28

Health v2 · maintenance only

69/100

  • Activity 96
  • Release rhythm 39
  • Longevity 59

Flags: no_license

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: 85.0
  • age_days: 839
  • days_rel: 324
  • days_push: 28
  • n_releases_24m: 3

Full methodology

Adoption not part of the score

8198 stars · 1210 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Duix Mobile is an open-source SDK for building real-time interactive AI avatars (digital humans) that run on-device on Android, iOS, tablets, and embedded screens. It lets developers plug in their own LLM, ASR, and TTS services to create low-latency, private conversational avatar experiences without cloud dependency.

Use cases

  • build a real-time interactive AI avatar on mobile
  • create an AI girlfriend or AI boyfriend companion app
  • deploy an on-premise digital human with low latency
  • add a talking virtual customer service agent to an app
  • build a virtual doctor or virtual tutor with a face and voice
  • run a digital human locally without cloud servers
  • integrate my own LLM, ASR, and TTS with an avatar

When to choose

  • you need on-device or on-premise avatar rendering with sub-second latency
  • you want to bring your own LLM, ASR, and TTS stack
  • privacy or poor-network resilience requires local processing
  • you target Android, iOS, tablets, or embedded/large screens

When to avoid

  • you need a fully managed cloud avatar API with hosted rendering
  • you require a permissive open-source license (license is custom/unspecified)
  • your target is web-only avatars rather than mobile/embedded
  • you want prebuilt avatar generation without integrating speech and LLM services

Facets

library · maturity active

speech-recognition tts llm-inference machine-learning sdk audio-processing image-processing artificial-intelligence chatbots mobile-development speech-processing computer-vision cross-platform cpp digital-human ai-avatar realtime-avatar on-device-ai conversational-ai lip-sync ai-companion embedded-screens ai-agents android ios mobile

5 sources

Member repositories

RepositoryRoleHealth v2
duixcom/Duix-Mobilemain69

For agents

markdown · JSON · MCP: product_card(name="duixcom/Duix-Mobile")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem